Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
wat10000
8 months ago
|
parent
|
context
|
favorite
| on:
Show HN: AutoThink – Boosts local LLM performance ...
If compute is limited, then dedicating more resources to the questions that are more likely to need it will increase correctness overall, even if it may decrease correctness for some individual responses.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: